[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-03-06。"],[[["AlloyDB AI provides machine learning capabilities to AlloyDB for PostgreSQL and AlloyDB Omni, allowing users to apply semantic and predictive power to their data."],["The platform includes a customized `vector` extension for storing and querying embeddings, as well as the `alloydb_scann` extension for efficient nearest-neighbor indexing, using algorithms like ScaNN."],["AlloyDB AI extends PostgreSQL with functions like `Invoke predictions` and `Generate embeddings`, which allow for querying models using SQL and translating text prompts into numerical vectors, respectively."],["Users can leverage the `embedding()` and `google_ml.embedding()` functions to query Vertex AI models, including the use of text embeddings, as well as custom hosted or third-party models."],["AlloyDB's integration with Vertex AI enables applications to invoke predictions using any model in the Vertex AI Model Garden and to generate embeddings using the `text-embedding-005` English models."]]],[]]